论文标题
NASIRT：基于实例级复杂性信息的基于汽车的学习
NASirt: AutoML based learning with instance-level complexity information
论文作者
论文摘要
设计足够和精确的神经体系结构是一项艰巨的任务，通常由高度专业的人员完成。 Automl是一个机器学习领域，旨在以自动化的方式生成良好的性能模型。诸如从生物分析获得的光谱数据通常具有许多重要信息，并且由于其图像样形状，这些数据特别适合卷积神经网络（CNN）。在这项工作中，我们提出了NASIRT，这是一种基于神经体系结构搜索（NAS）的汽车方法，可找到光谱数据集的高精度CNN体系结构。所提出的方法依赖于项目响应理论（IRT）从实例级别（例如歧视和难度）获得特征，并且能够定义高级性能的子模型的等级。为了通过不同的光谱数据集证明该方法的性能，进行了几项实验。将精度结果与其他基准方法进行比较，例如高性能，手动制作的CNN和自动keras Automl工具。结果表明，在大多数情况下，我们的方法的表现要比基准测试更好，达到平均准确性高达97.40％。
Designing adequate and precise neural architectures is a challenging task, often done by highly specialized personnel. AutoML is a machine learning field that aims to generate good performing models in an automated way. Spectral data such as those obtained from biological analysis have generally a lot of important information, and these data are specifically well suited to Convolutional Neural Networks (CNN) due to their image-like shape. In this work we present NASirt, an AutoML methodology based on Neural Architecture Search (NAS) that finds high accuracy CNN architectures for spectral datasets. The proposed methodology relies on the Item Response Theory (IRT) for obtaining characteristics from an instance level, such as discrimination and difficulty, and it is able to define a rank of top performing submodels. Several experiments are performed in order to demonstrate the methodology's performance with different spectral datasets. Accuracy results are compared to other benchmarks methods, such as a high performing, manually crafted CNN and the Auto-Keras AutoML tool. The results show that our method performs, in most cases, better than the benchmarks, achieving average accuracy as high as 97.40%.
